Related posts
Guillermo Rauch
x.com
We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.
reviewer luna gateway
The the words it uses that this site has seen
least often elsewhere. Posts are matched on those words alone —
nothing here is a summary of this one.
Sources
All Writing x.com Recommends GitHub Korrents Blog Site
Top people
David Crawshaw
Guillermo Rauch
Chris Tate
Simon Willison
John Resig
Ismail Ghallou
Alon Levy
Jeff Geerling
Ben Kuhn
George Monbiot
Paul Millerd
Maciej Cegłowski
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
19 September
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
Looks like today may be a record day for token volume % of open models on Vercel AI Gateway: 🟦 Open 78.4% 🟨 Closed 21.6% While spend 💲 usually tells a different story, #3 and #4 today are Moonshot AI & DeepSeek. Adding Z.ai, their combined spend surpasses OpenAI (#2). (Do note that's the spend for inference of the model across providers (mostly in the US), not revenue going directly to the open weight labs.) OpenAI Related
12 September
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
https://t.co/OL0LzGsXKY can now orchestrate subagents with different models & reasoning efforts. e.g: Fable planning and Grok executing. Fable is a genius, Grok is a fast workhorse. ① Simple. 𝙰𝙶𝙴𝙽𝚃𝚂.𝚖𝚍 or your prompt can indicate this preference. ② Steer as you please. It’s extremely enjoyable to use. You just talk to the agent and interrupt at will. Worth noting this works with any model, any gateway. No fancy server-side routing. Just harnessing (no pun intended) the model’s intelligence and ability to orchestrate. Quoting @fazxes fx v0.0.9 Use a frontier model to steer, then hand implementation to a fast workhorse. • Give each subagent its own model and reasoning effort • Subagents keep working while you steer • Send feedback to subagents mid-task • Switch models with Ctrl+P without losing your draft or images • New convers… Related
6 September
Engineer at Vercel Labs as of 2026. Ships a steady stream of small developer tools — agent-browser, portless, json-render, native-sdk, the v0 SDK — and lists every one of them at ctate.dev.
The spectrum between Luna and Astra is astounding Most work (~95%) can be done with Luna (specifically xhigh, fast) That ~5% where Astra is needed for optimization-maxxing design, performance, polish will change the world Related
4 September
Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.
Got access to GPT-6 Astra. Want to see some pelicans? Yeah you want to see some pelicans... here's a grid comparing Astra to GPT-5.6 Sol, Terra, and Luna OpenAI Related
JavaScript programmer; creator of the jQuery library, author of Secrets of the JavaScript Ninja, and long-time engineer at Khan Academy.
I love giving Fable problems that I 100% would've never done otherwise, such as collecting Japanese prints out of static image auction catalogs written entirely in Japanese. Uses OpenCV to do segmenting, GPT-5.6 Luna to do text extraction + translation. OpenAI Related
3 September
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
Their words
Points all coding agents to AI Gateway, getting you 100% uptime, observability, budgets, and ease of switching.
Show the whole quote
x.com
24 August
Engineer at Vercel Labs as of 2026. Ships a steady stream of small developer tools — agent-browser, portless, json-render, native-sdk, the v0 SDK — and lists every one of them at ctate.dev.
Their words
openai/gpt-5.6-luna-fast xhigh is *really* good at boring web dev tasks eg. migrations, ports, verifying work with agent-browser
Show the whole quote
x.com
21 August
Moroccan senior frontend developer writing at smakosh.com; builds side projects and client work under Smakosh LLC.
10 August
Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.
Anthropic OpenAI
Their words
Claude Haiku is my current least favorite model - it hallucinates wildly, and is out-performed now by other similarly priced models like GPT-5.6-Luna
Even worse: it seems to still be used by the Claude Code WebFetch tool, which means hallucination risk any time you fetch a URL!
Show the whole quote
@simonw on X x.com
30 July
Software engineer; co-founder and former CTO of Tailscale, previously on the Go team at Google.
The funniest model limit I run into with Shelley is we let the model choose subagent models. All models today seem to be bad at this without guidance. E.g. gpt-5.6-sol xhigh will spin up sonnet to make a key architectural decision. Fable will defer to luna. OpenAI Related
25 July
Writes Pedestrian Observations on public transit and why infrastructure costs what it does; a pure mathematician by training, comparing how different countries build.
23 July
Developer, author and YouTuber covering Raspberry Pi, homelab hardware and Ansible automation. Author of Ansible for DevOps.
7 May
Software engineer; co-founder and former CTO of Tailscale, previously on the Go team at Google.
From one piece
The agent principal-agent problem
2 beliefs, in the piece's order there
24 April
Software engineer and writer; former CTO of Wave, now at Anthropic. Blogs at benkuhn.net on attention, engineering management and doing hard things well.
8 April
Guardian columnist and environmental campaigner; wrote Feral and Regenesis, and argues for rewilding and against the food system as it is.
22 March
Software engineer; co-founder and former CTO of Tailscale, previously on the Go team at Google.
21 March 2025
Writer and former McKinsey/BCG strategy consultant; author of The Pathless Path and Good Work, about leaving the default career track. Publishes the Boundless newsletter and podcast.
Their words
A series of autobiographical essays exploring wandering, uncertainty, memory, desire, and place—embracing the unknown as a gateway to self-transcendence.
Show the whole quote
pathlesspath.com
24 May 2024
Founder of Pinboard; writes Idle Words — talks and essays on the web, aviation, politics and travel.
30 April 2023
Statistician at Carnegie Mellon; writes on complex systems, machine learning and inference, and has kept a books-read notebook since 2000 that is now thousands of entries long.
Their words
Mind candy fantasy / campus novel, in which Yale is literally a gateway to Hell.
Show the whole quote
bactra.org
15 April 2023
Software engineer who worked on Chrome and Polymer at Google, and writes about the web, emoji and Elm at meowni.ca.
Do y’all remember how no matter how you started a Pandora station you’d always get country within an hour? It would play a Tom Petty and bam! Gateway to country! Anyway I’m at a cover band show where Tom Petty is sandwiched between the Smiths and the Pixies Related
Nothing matches. Show everything
A korrent is a belief a person has stated in their own words: one
sentence stating the claim, backed by a quote and a source, kept at
korrents.com .
Under a name here, the quoted block is what they actually said.
The korrent beneath it is the claim those words support, in
korrents' wording — tap it to see the record, its source, and who
else holds it.
Nobody here wrote their own korrents. They are compiled from public
statements, and a person can change their mind, which is recorded too.
Got it
About the English under a post
Some people here publish in a language other than English. Where they
do, this site shows a machine translation beneath the post, in
this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the
serif above is exactly what the person published, and it is what to
quote them on. A translation can be wrong in ways that matter,
especially about tone.
Only the post's own words are translated. A quoted post, a linked
article and a belief on korrents.com
are left in their original language.
Got it